Training in progress, step 14000, checkpoint
Browse files- checkpoint-14000/added_tokens.json +5 -0
- checkpoint-14000/config.json +46 -0
- checkpoint-14000/merges.txt +0 -0
- checkpoint-14000/optimizer.pt +3 -0
- checkpoint-14000/pytorch_model.bin +3 -0
- checkpoint-14000/rng_state.pth +3 -0
- checkpoint-14000/scheduler.pt +3 -0
- checkpoint-14000/special_tokens_map.json +6 -0
- checkpoint-14000/tokenizer_config.json +7 -0
- checkpoint-14000/trainer_state.json +235 -0
- checkpoint-14000/training_args.bin +3 -0
- checkpoint-14000/vocab.json +0 -0
checkpoint-14000/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<bos>": 40478,
|
3 |
+
"<eos>": 40479,
|
4 |
+
"<pad>": 40480
|
5 |
+
}
|
checkpoint-14000/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-gpt",
|
3 |
+
"afn": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"OpenAIGPTForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"id2label": {
|
10 |
+
"0": "entailment",
|
11 |
+
"1": "neutral",
|
12 |
+
"2": "contradiction"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"contradiction": 2,
|
17 |
+
"entailment": 0,
|
18 |
+
"neutral": 1
|
19 |
+
},
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "openai-gpt",
|
22 |
+
"n_ctx": 512,
|
23 |
+
"n_embd": 768,
|
24 |
+
"n_head": 6,
|
25 |
+
"n_layer": 12,
|
26 |
+
"n_positions": 512,
|
27 |
+
"n_special": 0,
|
28 |
+
"pad_token_id": 40480,
|
29 |
+
"predict_special_tokens": true,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"resid_pdrop": 0.1,
|
32 |
+
"summary_activation": null,
|
33 |
+
"summary_first_dropout": 0.1,
|
34 |
+
"summary_proj_to_labels": true,
|
35 |
+
"summary_type": "cls_index",
|
36 |
+
"summary_use_proj": true,
|
37 |
+
"task_specific_params": {
|
38 |
+
"text-generation": {
|
39 |
+
"do_sample": true,
|
40 |
+
"max_length": 50
|
41 |
+
}
|
42 |
+
},
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.33.0.dev0",
|
45 |
+
"vocab_size": 40481
|
46 |
+
}
|
checkpoint-14000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6618bac7ee072fe768bd01f9779d897ef4bf6e79d2d3a15810841a3fa0044e03
|
3 |
+
size 932401285
|
checkpoint-14000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f01f4f4bcb8c1c12c787b5c17ed15e4ca138485283c23caa9e444d57b65aa120
|
3 |
+
size 466205145
|
checkpoint-14000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ee62a93d597ae5e815fccf41609d36575ca1eea0af8011f70418c124dfe61dd
|
3 |
+
size 14575
|
checkpoint-14000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ed78b8730d393b09731520cb16087c882367544f92a2ec98e71268506c4cbca
|
3 |
+
size 627
|
checkpoint-14000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<bos>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-14000/tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"padding_side": "left",
|
5 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-14000/trainer_state.json
ADDED
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.088543176651001,
|
3 |
+
"best_model_checkpoint": "/kaggle/output/checkpoint-12000",
|
4 |
+
"epoch": 0.5704041720990873,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 14000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2.7777777777777777e-11,
|
14 |
+
"loss": 1.2076,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 2.7750000000000004e-08,
|
20 |
+
"loss": 1.1301,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"eval_accuracy": 0.3321357285429142,
|
26 |
+
"eval_loss": 1.1047232151031494,
|
27 |
+
"eval_runtime": 50.8344,
|
28 |
+
"eval_samples_per_second": 98.555,
|
29 |
+
"eval_steps_per_second": 12.334,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.08,
|
34 |
+
"learning_rate": 5.5527777777777784e-08,
|
35 |
+
"loss": 1.1286,
|
36 |
+
"step": 2000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.08,
|
40 |
+
"eval_accuracy": 0.3377245508982036,
|
41 |
+
"eval_loss": 1.1038333177566528,
|
42 |
+
"eval_runtime": 50.8114,
|
43 |
+
"eval_samples_per_second": 98.6,
|
44 |
+
"eval_steps_per_second": 12.34,
|
45 |
+
"step": 2000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.12,
|
49 |
+
"learning_rate": 8.327777777777778e-08,
|
50 |
+
"loss": 1.1214,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12,
|
55 |
+
"eval_accuracy": 0.3409181636726547,
|
56 |
+
"eval_loss": 1.103529930114746,
|
57 |
+
"eval_runtime": 50.8258,
|
58 |
+
"eval_samples_per_second": 98.572,
|
59 |
+
"eval_steps_per_second": 12.336,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.16,
|
64 |
+
"learning_rate": 1.1105555555555557e-07,
|
65 |
+
"loss": 1.1249,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.16,
|
70 |
+
"eval_accuracy": 0.3469061876247505,
|
71 |
+
"eval_loss": 1.1000434160232544,
|
72 |
+
"eval_runtime": 50.6414,
|
73 |
+
"eval_samples_per_second": 98.931,
|
74 |
+
"eval_steps_per_second": 12.381,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.2,
|
79 |
+
"learning_rate": 1.3880555555555558e-07,
|
80 |
+
"loss": 1.1206,
|
81 |
+
"step": 5000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.2,
|
85 |
+
"eval_accuracy": 0.34171656686626745,
|
86 |
+
"eval_loss": 1.0996097326278687,
|
87 |
+
"eval_runtime": 50.6956,
|
88 |
+
"eval_samples_per_second": 98.825,
|
89 |
+
"eval_steps_per_second": 12.368,
|
90 |
+
"step": 5000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.24,
|
94 |
+
"learning_rate": 1.6658333333333335e-07,
|
95 |
+
"loss": 1.1161,
|
96 |
+
"step": 6000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.24,
|
100 |
+
"eval_accuracy": 0.3590818363273453,
|
101 |
+
"eval_loss": 1.096977710723877,
|
102 |
+
"eval_runtime": 50.5826,
|
103 |
+
"eval_samples_per_second": 99.046,
|
104 |
+
"eval_steps_per_second": 12.396,
|
105 |
+
"step": 6000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.29,
|
109 |
+
"learning_rate": 1.9433333333333334e-07,
|
110 |
+
"loss": 1.1138,
|
111 |
+
"step": 7000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.29,
|
115 |
+
"eval_accuracy": 0.3532934131736527,
|
116 |
+
"eval_loss": 1.0949815511703491,
|
117 |
+
"eval_runtime": 50.5604,
|
118 |
+
"eval_samples_per_second": 99.089,
|
119 |
+
"eval_steps_per_second": 12.401,
|
120 |
+
"step": 7000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 0.33,
|
124 |
+
"learning_rate": 2.2211111111111114e-07,
|
125 |
+
"loss": 1.1135,
|
126 |
+
"step": 8000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.33,
|
130 |
+
"eval_accuracy": 0.36327345309381237,
|
131 |
+
"eval_loss": 1.093558430671692,
|
132 |
+
"eval_runtime": 50.608,
|
133 |
+
"eval_samples_per_second": 98.996,
|
134 |
+
"eval_steps_per_second": 12.389,
|
135 |
+
"step": 8000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.37,
|
139 |
+
"learning_rate": 2.4986111111111113e-07,
|
140 |
+
"loss": 1.1063,
|
141 |
+
"step": 9000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.37,
|
145 |
+
"eval_accuracy": 0.35548902195608784,
|
146 |
+
"eval_loss": 1.0992107391357422,
|
147 |
+
"eval_runtime": 50.5434,
|
148 |
+
"eval_samples_per_second": 99.123,
|
149 |
+
"eval_steps_per_second": 12.405,
|
150 |
+
"step": 9000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.41,
|
154 |
+
"learning_rate": 2.776388888888889e-07,
|
155 |
+
"loss": 1.1083,
|
156 |
+
"step": 10000
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.41,
|
160 |
+
"eval_accuracy": 0.3836327345309381,
|
161 |
+
"eval_loss": 1.0920206308364868,
|
162 |
+
"eval_runtime": 50.5559,
|
163 |
+
"eval_samples_per_second": 99.098,
|
164 |
+
"eval_steps_per_second": 12.402,
|
165 |
+
"step": 10000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.45,
|
169 |
+
"learning_rate": 3.053888888888889e-07,
|
170 |
+
"loss": 1.1044,
|
171 |
+
"step": 11000
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.45,
|
175 |
+
"eval_accuracy": 0.38762475049900197,
|
176 |
+
"eval_loss": 1.0904459953308105,
|
177 |
+
"eval_runtime": 50.9725,
|
178 |
+
"eval_samples_per_second": 98.288,
|
179 |
+
"eval_steps_per_second": 12.301,
|
180 |
+
"step": 11000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.49,
|
184 |
+
"learning_rate": 3.331666666666667e-07,
|
185 |
+
"loss": 1.1019,
|
186 |
+
"step": 12000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.49,
|
190 |
+
"eval_accuracy": 0.3912175648702595,
|
191 |
+
"eval_loss": 1.088543176651001,
|
192 |
+
"eval_runtime": 50.8297,
|
193 |
+
"eval_samples_per_second": 98.564,
|
194 |
+
"eval_steps_per_second": 12.335,
|
195 |
+
"step": 12000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.53,
|
199 |
+
"learning_rate": 3.609166666666667e-07,
|
200 |
+
"loss": 1.1032,
|
201 |
+
"step": 13000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.53,
|
205 |
+
"eval_accuracy": 0.3435129740518962,
|
206 |
+
"eval_loss": 1.0940682888031006,
|
207 |
+
"eval_runtime": 51.0031,
|
208 |
+
"eval_samples_per_second": 98.229,
|
209 |
+
"eval_steps_per_second": 12.293,
|
210 |
+
"step": 13000
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 0.57,
|
214 |
+
"learning_rate": 3.886944444444445e-07,
|
215 |
+
"loss": 1.1006,
|
216 |
+
"step": 14000
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.57,
|
220 |
+
"eval_accuracy": 0.36826347305389223,
|
221 |
+
"eval_loss": 1.0924910306930542,
|
222 |
+
"eval_runtime": 51.2753,
|
223 |
+
"eval_samples_per_second": 97.708,
|
224 |
+
"eval_steps_per_second": 12.228,
|
225 |
+
"step": 14000
|
226 |
+
}
|
227 |
+
],
|
228 |
+
"logging_steps": 1000,
|
229 |
+
"max_steps": 10000000,
|
230 |
+
"num_train_epochs": 408,
|
231 |
+
"save_steps": 1000,
|
232 |
+
"total_flos": 2.9264971825152e+16,
|
233 |
+
"trial_name": null,
|
234 |
+
"trial_params": null
|
235 |
+
}
|
checkpoint-14000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:933e5c21c45262af343f5d708824cb21f8d339a9e2662221f8b52a4157df35fa
|
3 |
+
size 4091
|
checkpoint-14000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|